{ "openapi": "3.0.1", "info": { "title": "Bulk Image and File Downloader - Scan Pages, ZIP", "description": "Download images, PDFs and files in bulk from direct links or scan any web page for media. Saves every file to storage with a public link, optional ZIP archive.", "version": "0.0", "x-build-id": "bPYcXN8nPhc8jVrcT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tiger19935~bulk-image-file-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tiger19935-bulk-image-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tiger19935~bulk-image-file-downloader/runs": { "post": { "operationId": "runs-sync-tiger19935-bulk-image-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tiger19935~bulk-image-file-downloader/run-sync": { "post": { "operationId": "run-sync-tiger19935-bulk-image-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "URLs", "type": "array", "description": "Web pages to scan (default) or direct file links (turn off Scan pages).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "scanPages": { "title": "Scan pages for files", "type": "boolean", "description": "On: each URL is a web page and the actor finds the files on it. Off: each URL is a direct link to a file.", "default": true }, "fileTypes": { "title": "File types", "type": "array", "description": "Which kinds of files to collect when scanning pages. Images are taken from img tags, srcset, social preview tags and icons; other types from links and media tags.", "items": { "type": "string", "enum": [ "images", "documents", "archives", "audio", "video" ], "enumTitles": [ "Images (JPG, PNG, WebP, SVG ...)", "Documents (PDF, Word, Excel, PowerPoint, CSV ...)", "Archives (ZIP, RAR, 7Z ...)", "Audio (MP3, WAV ...)", "Video (MP4, WebM ...)" ] }, "default": [ "images" ] }, "maxFiles": { "title": "Max files", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Stop after this many files have been downloaded (billing applies per downloaded file).", "default": 100 }, "maxFilesPerPage": { "title": "Max files per page", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Only the first N candidate files found on each page are used.", "default": 100 }, "dedupe": { "title": "Remove duplicates", "type": "boolean", "description": "Skip files with identical content (compared by SHA-256). Duplicates are not billed.", "default": true }, "minWidth": { "title": "Minimum image width (px)", "minimum": 0, "type": "integer", "description": "Skip smaller images such as icons and tracking pixels.", "default": 0 }, "minHeight": { "title": "Minimum image height (px)", "minimum": 0, "type": "integer", "description": "Skip images shorter than this.", "default": 0 }, "minFileSizeKb": { "title": "Minimum file size (KB)", "minimum": 0, "type": "integer", "description": "Skip files smaller than this.", "default": 0 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip files larger than this.", "default": 25 }, "imageFormat": { "title": "Convert images to", "enum": [ "original", "webp", "jpeg", "png" ], "type": "string", "description": "Keep originals or convert all raster images to one format.", "default": "original" }, "maxImageDimension": { "title": "Resize images (longest side, px)", "minimum": 0, "maximum": 8000, "type": "integer", "description": "Shrink larger images so that neither side exceeds this. 0 keeps the original size.", "default": 0 }, "imageQuality": { "title": "JPEG / WebP quality", "minimum": 1, "maximum": 100, "type": "integer", "description": "Compression quality 1-100 for converted images.", "default": 85 }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Only collect files hosted on the same domain as the page. CDN-hosted images are skipped when on.", "default": false }, "urlIncludePattern": { "title": "URL must match (regex)", "type": "string", "description": "Optional regular expression. Only file URLs that match are downloaded, for example /uploads/ or \\.pdf$" }, "urlExcludePattern": { "title": "URL must not match (regex)", "type": "string", "description": "Optional regular expression. File URLs that match are skipped, for example thumb|logo|sprite" }, "createZip": { "title": "Create a ZIP archive", "type": "boolean", "description": "Also save all files as one files.zip in the key-value store (up to 400 MB).", "default": false }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many files are downloaded at once.", "default": 6 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }